Ollama Rules
Run large language models locally. Pull, run, create, and manage AI models on your own hardware.
3 rules
API Integration Rules
Intermediate
Standards for integrating Ollama's REST API into applications — health checks, error handling, timeout configuration, streaming patterns, and request parameter validation.
globs: **/*.ts, **/*.js, **/*.py
api, error-handling, health-check, timeouts
View Rule
Modelfile Standards
Intermediate
Enforce consistent Ollama Modelfile structure with required sections, parameter documentation, proper system prompts, and template configuration for reliable custom model builds.
globs: **/Modelfile*, **/modelfile*
modelfile, standards, configuration, naming
View Rule
Resource Management Rules
Advanced
Enforce GPU memory, disk storage, and concurrent request limits for Ollama deployments — preventing out-of-memory crashes, storage exhaustion, and performance degradation.
globs: **/ollama*, **/.env*
resource-management, gpu-memory, concurrency, storage
View Rule